Although convolutional networks (ConvNets) have enjoyed great success in computer vision (CV), it suffers from capturing global information crucial to dense prediction tasks such as object detection and segmentation. In this work, we innovatively propose ConTNet (Convolution-Transformer Network), combining transformer with Con-vNet architectures to provide large receptive fields. Unlike the recently-proposed transformer-based models (e.g., ViT, DeiT) that are sensitive to hyper-parameters and extremely dependent on a pile of data augmentations when trained from scratch on a midsize dataset (e.g., ImageNet1k), Con-TNet can be optimized like normal ConvNets (e.g., ResNet) and preserve an outstanding robustness. It is also worth pointing that, given identical strong data augmentations, the performance improvement of ConTNet is more remarkable than that of ResNet. We present its superiority and effectiveness on image classification and downstream tasks. For example, our ConTNet achieves 81.8% top-1 accuracy on ImageNet which is the same as DeiT-B with less than 40% computational complexity. ConTNet-M also outperforms ResNet50 as the backbone of both Faster-RCNN (by 2.6%) and Mask-RCNN (by 3.2%) on COCO2017 dataset. We hope that ConTNet could serve as a useful backbone for CV tasks and bring new ideas for model design. The code will be released at https://github.com/yanhao-tian/ConTNet.
Image classification and object detection are two computer vision techniques that are currently commonly used. In this paper, convolutional neural network (CNN) and region-based CNN (RCNN) are used as examples to analyze and compare image classification and object detection. This paper will analyze the architectural characteristics and application scenarios of these two algorithms and analyzes the different characteristics of these two technologies in medical technology applications. CNN is an infrastructure classification algorithm, and image classification tasks are more common in medical image processing. RCNN is the development of CNN. Object detection technology can directly detect the presence and location of the lesion in medical images with RCNN. Combining the algorithms of the two techniques can also achieve some more complex image processing goals.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.